1#!/usr/bin/env ruby 2 3# converts the patterns from upstream git repository to TeX-friendly form 4 5path = File.expand_path("../../hyph-utf8/tex/generic/hyph-utf8/patterns/tex") 6 7# http://git.savannah.gnu.org/cgit/smc.git/tree/hyphenation 8languages = %w(as bn gu hi kn ml mr or pa ta te) 9#languages = %w(as) 10 11languages.each do |language_code| 12 filename = "hyph_#{language_code}_IN.dic" 13 # git://git.sv.gnu.org/smc/hyphenation.git 14 # url = "http://git.savannah.gnu.org/cgit/smc/hyphenation.git/plain/#{language_code}_IN/#{filename}" 15 url = "https://raw.githubusercontent.com/santhoshtr/hyphenation/master/#{language_code}_IN/#{filename}" 16 system("wget -N -c -P original #{url}") 17 18 lines = IO.readlines("original/#{filename}", '.').join(""). 19# a few temporary patches - remove double newline at the end of file, remove trailing spaces, remove double "GENERAL RULE" comment in the file 20 gsub(/\n\n$/, "\n").gsub(/[ ]*\n/, "\n"). 21 # gsub(/(% GENERAL RULE)\n% GENERAL RULE/, '\1'). 22# end of temporary patches 23 gsub(/UTF-8/, "% These patterns originate from\n% https://github.com/santhoshtr/hyphenation/)\n% and have been adapted for hyph-utf8 (for use in TeX).\n%"). 24 gsub(/% GENERAL RULE/, "\\patterns{\n% GENERAL RULE") + "}\n" 25 26 filename_out = "#{path}/hyph-#{language_code}.tex" 27 file_out = File.open(filename_out, "w") 28 file_out.puts(lines) 29 file_out.close 30end 31